Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13393
    Prev
    Next
    INDEX
    Explanations

    structure and syntax elements related to code or programming logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fast
    -0.49
     not
    -0.48
    地
    -0.48
     —
    -0.47
    ,
    -0.46
     non
    -0.43
     thanks
    -0.42
     er
    -0.41
     to
    -0.40
     sun
    -0.40
    POSITIVE LOGITS
    expandindo
    1.01
    NameInMap
    0.91
     disambiguazione
    0.89
     protoimpl
    0.88
    rungsseite
    0.85
    AddTagHelper
    0.84
    InitVars
    0.83
    protoimpl
    0.82
     resourceCulture
    0.80
    featureID
    0.78
    Activations Density 0.179%

    No Known Activations